Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for discovering relevant concepts in a semantic graph of concepts

a semantic graph and concept discovery technology, applied in the field of semantic web, can solve the problems of not providing enough valuable value, and difficult to find the most likely points to a solution

Active Publication Date: 2020-02-11
HYPIOS +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the millions of existing concepts known to humanity, finding those that are the most likely to point to a solution remains very difficult.
However, it appears that these systems offer only a partial view of the conceptual space that is driven mostly by obvious associations with initial concepts, and so they still do not provide sufficiently valuable results, enriching for the user.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for discovering relevant concepts in a semantic graph of concepts
  • Method for discovering relevant concepts in a semantic graph of concepts
  • Method for discovering relevant concepts in a semantic graph of concepts

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

Environment

[0035]With reference to FIG. 1, the invention concerns a method for identifying in a given semantic graph of linked concepts a set of concepts matching the content of a text, the semantic graph of linked concepts being stored in an equipment 10 connected through a network 20, particularly the internet

[0036]However, the invention is not limited to a specific environment, and the equipment 10 is shall be understood as any “source(s)” from which the semantic graph of linked concepts could be accessed through the network 20. The equipment 10 may include one or more piece(s) of equipment.

[0037]In this case the network 20 is Internet, the equipment 10 is notably a Web server.

[0038]Indeed, the already mentioned large semantic graphs of linked concepts from general encyclopedic knowledge (e.g. DBpedia, Freebase, etc.) are hosted in the form of Graph data stores, in particular RDF databases, in one or more remote servers. The given semantic graph of linked concepts may be a partic...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention is related to a method for identifying in a given semantic graph of linked concepts a set of concepts matching the content of a text, the semantic graph of linked concepts being stored in at least one equipment connected to a network, the methods comprising of the following steps:inputting a sample text in natural language at a workstation connected to the network;performing a semantic analysis of the sample text to extract a set of initial concepts belonging to the given semantic graph;accessing the equipment to identify a list of candidate concepts in the given semantic graph, the candidate concepts being the concepts of the semantic graph within a given maximum distance according to a given distance function away from an initial concept;calculating for each candidate concept a proximity score representative of the distances between the candidate concept and each initial concept;identifying as matching concepts the candidate concepts with the highest proximity score.

Description

FIELD OF THE INVENTION[0001]The invention concerns the field of the Semantic Web.[0002]More precisely, the invention relates to a method for identifying in a given semantic graph of linked concepts a set of concepts matching the content of a text.BACKGROUND OF THE INVENTION[0003]The Semantic Web is a set of technologies, which aim to make the content of the resources of the Web accessible and usable by machines (in particular thanks to programs and software agents) through a system of data and metadata.[0004]RDF (Resource Description Framework) is the language that can be used for resource representation in a semantically rich way. RDF is a data model of semantic graph (a collection of RDF statements can intrinsically represent a graph of linked “concepts”), designed for helping to describe the resources on the Web and their metadata, allowing automated processing. It is implemented using a variety of syntax formats, but XML is generally preferred.[0005]The mentioned items of a sema...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(United States)
IPC IPC(8): G06F16/00G06F16/2452G06F16/901
CPCG06F40/30G06F16/24522G06F16/9024
Inventor STANKOVIC, MILANLAUBLET, PHILIPPE
Owner HYPIOS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products